AI Needs Memory - Here's How It Works

Explore the foundational architectural decisions that determine whether AI agents deliver lasting value or become expensive technical debt in this 29-minute conference talk. Discover the core tradeoffs between flexibility and performance, examine memory patterns essential for agent reliability, and learn to architect systems that evolve with the rapidly changing AI landscape. Focus on understanding what problems agents fundamentally solve—automating complex, multi-step workflows—and design memory and coordination systems around those core needs rather than getting caught up in today's specific technologies. Gain a practical framework for making architectural decisions that will serve you well regardless of which models, frameworks, or tools become dominant, with insights from a Principal Machine Learning Engineer who has built enterprise-scale GenAI platforms and authored "What Are AI Agents?" for O'Reilly.